Skip to content

Commit

Permalink
Review and update boolean annotations in use (related to #141) (#143)
Browse files Browse the repository at this point in the history 
* Update boolean biosample annotation props

* Update isStranded

* Close issue #61

* Add changes

* Define isPairedEnd (issue #50)

* Add changes

* Update failedQC prop

* Add changes

Co-authored-by: nf-osi[bot] <[email protected]>
  • Loading branch information
@anngvu @nfosi-service
anngvu and nfosi-service authored May 6, 2022
1 parent 305f14d commit f4d789c
Show file tree
Hide file tree
Showing 5 changed files with 90 additions and 36 deletions.
14 changes: 8 additions & 6 deletions NF.csv
View file
Original file line number Diff line number Diff line change
Expand Up @@ -197,7 +197,7 @@ reporterSubstance,A gene which produces an easily assayed phenotype. Often used
immunoAssayType,Type of immuno assay,"ChIPseq, ATAC-seq",,TRUE,,immunoAssay,,,,immunoAssayType,Property,Assay,annotationProperty,,,,
runType,Is the sequencing run single or paired end?,"singleEnd, pairedEnd","readPair,isStranded,readPairOrientation,readStrandOrigin,readLength,readDepth",FALSE,Sage Bionetworks,ngs,,,,runType,Property,Assay,annotationProperty,ngsParameter,Run_Type,,
readPair,The read of origin,"1, 2",,FALSE,,ngs,,,,readPair,Property,Assay,annotationProperty,ngsParameter,Read_Pair,,
isStranded,Whether or not the library is stranded. (Note: TRUE = Yes; FALSE = No),"TRUE, FALSE",,FALSE,,ngs,,,,isStranded,Property,Assay,annotationProperty,ngsParameter,,,
isStranded,Whether or not the library is stranded (Yes; No),"Yes, No",,FALSE,,ngs,,,,isStranded,Property,Assay,annotationProperty,ngsParameter,,,
readPairOrientation,The relative orientation of the reads in a paired-end protocol,"inward, outward, matching, fr-firststrand",,FALSE,,ngs,,,,readPairOrientation,Property,Assay,annotationProperty,ngsParameter,Read_Pair_Orientation,,
readStrandOrigin,The strand from which the read originates in a strand-specific protocol,"forward, reverse",,FALSE,,ngs,,,,readStrandOrigin,Property,Assay,annotationProperty,ngsParameter,Read_Strand_Origin,,
libraryPrep,The general strategy by which the library was prepared,"rRNAdepletion, polyAselection, lncRNAenrichment, miRNAenrichment","libraryPreparationMethod,nucleicAcidSource,dissociationMethod",FALSE,,ngs,,,,libraryPrep,Property,Assay,annotationProperty,ngsParameter,Library_Prep,,
Expand All @@ -206,6 +206,7 @@ nucleicAcidSource,Source of the extracted nucleic acid used in the experiment,"b
dissociationMethod,Procedure by which a biological specimen is dissociated into individual cells or a cell suspension,"10x_v2, FACS, Fluidigm C1, drop-seq, inDrop, mouth pipette, bulk, enzymatic, mechanical, none",,FALSE,https://www.ebi.ac.uk/ols/ontologies/efo/terms?iri=http%3A%2F%2Fwww.ebi.ac.uk%2Fefo%2FEFO_0009088,ngs,,,,dissociationMethod,Property,Assay,annotationProperty,ngsParameter,Dissociation_Method,,
readLength,Number of base pairs (bp) sequenced for a read,,,FALSE,,ngs,,,,readLength,DataProperty,Assay,annotationProperty,ngsParameter,,,
readDepth,"If available, coverage statistic as output from bedtools coverage or samtools stats.",,,FALSE,Sage Bionetworks,ngs,,,,readDepth,DataProperty,Assay,annotationProperty,ngsParameter,,,
isPairedEnd,"(Legacy/deprecated annotation) Whether or not is paired-end sequencing (Yes; No). Note that this can be inferred as 'Yes' when runType=pairedEnd; current templates actually use runType to capture this info.","Yes, No",,FALSE,,ngs,,,,isPairedEnd,DataProperty,Assay,annotationProperty,ngsParameter,,,
head,The head is the anterior-most division of the body.,"","",FALSE,http://purl.obolibrary.org/obo/UBERON_0000033,bodyPart,,"","",Head,Class,Biosample,Body_Part,Body_Part,"","",""
lymph node,A bean-shaped organ surrounded by a connective tissue capsule.,"","",FALSE,http://purl.obolibrary.org/obo/NCIT_C12745,organ,,"","",Lymph_Node,Class,Biosample,Body_Part,Organ,"","",""
kidney,One of the two bean-shaped organs located on each side of the spine in the retroperitoneum.,"","",FALSE,http://purl.obolibrary.org/obo/NCIT_C12415,organ,,"","",Kidney,Class,Biosample,Body_Part,Organ,"","",""
Expand Down Expand Up @@ -479,11 +480,11 @@ bodyPart,"Sample location referring to a named area of the body, inclusive of gr
organ,A unique macroscopic (gross) anatomic structure that performs specific functions. It is composed of various tissues. An organ is part of an anatomic system or a body region.,"lymph node, kidney, skin, mammary gland, nerves, brain, blood, breast, colon, lung, liver, prostate, pancreas, ovary, spleen, bone marrow, Bursa Of Fabricius, nose",,FALSE,,experimentalData,,,,organ,Property,Biosample,annotationProperty,,Organ,,
individualIdSource,Database or repository to which individual ID maps,,,FALSE,,experimentalData,,,,individualIdSource,Property,Biosample,annotationProperty,,,,
tissue,A tissue is a mereologically maximal collection of cells that together perform physiological function.,"nerve tissue,optic nerve,serum,plasma,splenocyte,blood,primary tumor,embryonic tissue,meninges,bone marrow,Buccal Mucosa,Dorsal Root Ganglion,unspecified,whole brain,Buffy Coat,cerebral cortex,sciatic nerve,connective tissue,tumor-adjacent normal, PDX tissue, CDX tissue, metastatic/recurrent tumor, recurrent tumor, metastatic tumor, organoid, spheroid, microtissue",,FALSE,,experimentalData,,,,tissueType,Property,Biosample,annotationProperty,,Tissue,,
isCellLine,Boolean flag indicating whether or not sample source is a cell line. (Note: TRUE = Yes; FALSE = No),"TRUE, FALSE",,FALSE,,experimentalData,,,,isCellLine,DataProperty,Biosample,annotationProperty,,,,
isPrimaryCell,Boolean flag indicating whether or not cellType is primary (Note: TRUE = Yes; FALSE = No),"TRUE, FALSE",,FALSE,,experimentalData,,,,isPrimaryCell,DataProperty,Biosample,annotationProperty,,,,
isCellLine,Whether or not sample source is a cell line (Yes; No),"Yes, No",,FALSE,,experimentalData,,,,isCellLine,DataProperty,Biosample,annotationProperty,,,,
isPrimaryCell,Whether or not cellType is primary (Yes; No),"Yes, No",,FALSE,,experimentalData,,,,isPrimaryCell,DataProperty,Biosample,annotationProperty,,,,
cellType,A cell type is a distinct morphological or functional form of cell.,"Schwann cell precursor, B-lymphocytes, Embryonic stem cells, iPSC, iPSC-derived telencephalic organoids, GABAergic neurons, monocytes, microglia, macrophages, astrocytes, SH-SY5Y, GLUtamatergic neurons, NeuN+, NeuN-, epithelial, epithelial-like, fibroblast, round, lymphoblast, CD8+ T-Cells, arachnoid, meningioma, schwannoma, oligodendrocyte, schwann, iPSC-derived neuron, iPSC-derived glia, iPSC-derived astrocytes, monocyte-derived microglia, iPSC-derived neuronal progenitor cell, CD138+, CNON, teratoma",,FALSE,,experimentalData,,,list,cellType,DataProperty,Biosample,annotationProperty,,Cell,,
isMultiIndividual,Boolean flag indicating whether or not a file has data for multiple individuals (Note: TRUE = Yes; FALSE = No),"TRUE, FALSE",,TRUE,,experimentalData,,,,isMultiIndividual,DataProperty,Biosample,annotationProperty,,,,
isMultiSpecimen,Boolean flag indicating whether or not a file has data for multiple specimens (Note: TRUE = Yes; FALSE = No),"TRUE, FALSE",,TRUE,,experimentalData,,,,isMultiSpecimen,DataProperty,Biosample,annotationProperty,,,,
isMultiIndividual,Whether or not a file has data for multiple individuals (Yes; No),"Yes, No",,TRUE,,experimentalData,,,,isMultiIndividual,DataProperty,Biosample,annotationProperty,,,,
isMultiSpecimen,Whether or not a file has data for multiple specimens (Yes; No),"Yes, No",,TRUE,,experimentalData,,,,isMultiSpecimen,DataProperty,Biosample,annotationProperty,,,,
sex,"Phenotypic expression of chromosomal makeup that defines a study subject as male, female, or other.","Male, Female, Unknown",,FALSE,http://purl.obolibrary.org/obo/NCIT_C28421,experimentalData,,,,sex,Property,Biosample,annotationProperty,,Sex,,
species,The name of a species (typically a taxonomic group) of organism.,"Homo sapiens,Mus musculus,Mus musculus (humanized),Rattus norvegicus,Drosophila melanogaster,Rhesus macaque,Pan troglodytes,Gallus gallus,Sus scrofa,Oryctolagus cuniculus,Danio rerio",,FALSE,,experimentalData,,,,species,Property,Biosample,annotationProperty,,Species,one,
individualID,A unique identifier (non-PII) that represents the individual from which the data came. This could be a patient or animal ID.,,"sex,age,ageUnit,species,diagnosis,nf1Genotype,nf2Genotype",FALSE,,experimentalData,,,,individualID,Property,Biosample,annotationProperty,,,many,"Typically annotated with a single ID, but many allowed for, e.g. a clinical dataset that contains endpoint data for an entire cohort."
Expand All @@ -498,6 +499,7 @@ specimenPreparationMethod,"Term that represents preservation of the sample befor
age,A numeric value representing age of the individual. Use with ageUnit.,,ageUnit,FALSE,Sage Bionetworks,,,,,age,DataProperty,Biosample,annotationProperty,biosampleAnnotation,,,
ageUnit,"A time unit that can be used with a given age value, e.g. years.","days, months, years",,FALSE,Sage Bionetworks,,,,,ageUnit,Property,Biosample,annotationProperty,biosampleAnnotation,,,
bioSampleUsed,The biosample used.,,,,,,,,,,,,,,,,
isXenograft,Whether or not sample source is a xenograft (Yes; No),"Yes, No",,TRUE,,experimentalData,,,,isXenograft,DataProperty,Biosample,annotationProperty,,,,
raw counts,The number or amount of something.,"",assay,FALSE,http://purl.obolibrary.org/obo/NCIT_C25463,dataType,,"","",Raw_Counts,Class,Data,Data_Class,"","","",""
Volume,The amount of three dimensional space occupied by an object or the capacity of a space or container.,"",assay,FALSE,http://purl.obolibrary.org/obo/NCIT_C25335,dataType,,"","",Volume,Class,Data,Data_Class,"","","",""
Weight,The vertical force exerted by a mass as a result of gravity.,"",assay,FALSE,http://purl.obolibrary.org/obo/NCIT_C25208,dataType,,"","",Weight,Class,Data,Data_Class,"","","",""
Expand Down Expand Up @@ -643,7 +645,7 @@ reference sequence,Syntactic sequences that has a role as reference of an annota
dataSubtype,"Further qualification of dataType, which may be used to indicate the state of processing of the data, aggregation of the data, or presence of metadata.","normalized, dataMatrix, raw, processed, metadata, representative",,TRUE,,experimentalData,,,,dataSubtype,Property,Data,annotationProperty,,Data,one,
metadataType,"For files of dataSubtype: metadata, a description of the type of metadata in the file.","individual, biospecimen, assay, data dictionary, manifest, protocol",,FALSE,,experimentalData,,,,metadataType,Property,Data,annotationProperty,,,,
dataType,"A type of experimental, clinical, or other data. This typically refers to a high-level data type, that is paired with a specific assay. For example, a file of dataType of """"genomicVariants"""" might have an assay value of """"whole genome sequencing"""". ","Volume, Weight, Pharmacokinetic Study, genomicVariants, behavior process, metabolomics, image, geneExpression, isoformExpression, proteomics, kinomics, drugScreen, drugCombinationScreen, cellularPhysiology, chromatinActivity, surveyData, network, clinical, immunoassay, electrophysiology, raw counts, mask image",dataSubtype,TRUE,,experimentalData,,,,dataType,Property,Data,annotationProperty,,Data,one,
failedQC,Boolean flag indicating whether the sample or data failed QC checks (Note: TRUE = Yes; FALSE = No),"TRUE, FALSE",,TRUE,,experimentalData,,,,failedQC,DataProperty,Data,annotationProperty,,,,
failedQC,Whether the sample or data failed QC checks (Yes; No),"Yes, No",,TRUE,,experimentalData,,,,failedQC,DataProperty,Data,annotationProperty,,,,
Filename,The name of the file.,,"entityId,fileFormat",TRUE,Sage Bionetworks,NF,,,,fileName,Class,Data,annotationProperty,fileName,,one,Automatically filled when using the curator app.
programmingLanguage,A computer programming language,"Python, R, MATLAB, Java, C, C++, C#, Javascript, bash",,FALSE,Sage Bionetworks,,,,,programmingLanguage,Property,Data,annotationProperty,ngsParameter,,,
runtimePlatform,"Runtime platform or script interpreter dependencies (e.g. Java v1, Python 2.3).",,,FALSE,Sage Bionetworks,,,,,runtimePlatform,Property,Data,annotationProperty,ngsParameter,,,
Expand Down
98 changes: 74 additions & 24 deletions NF.jsonld
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5799,7 +5799,7 @@
{
"@id": "bts:IsStranded",
"@type": "rdfs:Class",
"rdfs:comment": "Whether or not the library is stranded. (Note: TRUE = Yes; FALSE = No)",
"rdfs:comment": "Whether or not the library is stranded (Yes; No)",
"rdfs:label": "IsStranded",
"rdfs:subClassOf": [
{
Expand All @@ -5811,10 +5811,10 @@
},
"schema:rangeIncludes": [
{
"@id": "bts:TRUE"
"@id": "bts:Yes"
},
{
"@id": "bts:FALSE"
"@id": "bts:No"
}
],
"sms:displayName": "isStranded",
Expand Down Expand Up @@ -6097,6 +6097,31 @@
"sms:required": "sms:false",
"sms:validationRules": []
},
{
"@id": "bts:IsPairedEnd",
"@type": "rdfs:Class",
"rdfs:comment": "(Legacy/deprecated annotation) Whether or not is paired-end sequencing (Yes; No). Note that this can be inferred as 'Yes' when runType=pairedEnd; current templates actually use runType to capture this info.",
"rdfs:label": "IsPairedEnd",
"rdfs:subClassOf": [
{
"@id": "bts:Ngs"
}
],
"schema:isPartOf": {
"@id": "http://schema.biothings.io"
},
"schema:rangeIncludes": [
{
"@id": "bts:Yes"
},
{
"@id": "bts:No"
}
],
"sms:displayName": "isPairedEnd",
"sms:required": "sms:false",
"sms:validationRules": []
},
{
"@id": "bts:Head",
"@type": "rdfs:Class",
Expand Down Expand Up @@ -11175,7 +11200,7 @@
{
"@id": "bts:IsCellLine",
"@type": "rdfs:Class",
"rdfs:comment": "Boolean flag indicating whether or not sample source is a cell line. (Note: TRUE = Yes; FALSE = No)",
"rdfs:comment": "Whether or not sample source is a cell line (Yes; No)",
"rdfs:label": "IsCellLine",
"rdfs:subClassOf": [
{
Expand All @@ -11187,10 +11212,10 @@
},
"schema:rangeIncludes": [
{
"@id": "bts:TRUE"
"@id": "bts:Yes"
},
{
"@id": "bts:FALSE"
"@id": "bts:No"
}
],
"sms:displayName": "isCellLine",
Expand All @@ -11200,7 +11225,7 @@
{
"@id": "bts:IsPrimaryCell",
"@type": "rdfs:Class",
"rdfs:comment": "Boolean flag indicating whether or not cellType is primary (Note: TRUE = Yes; FALSE = No)",
"rdfs:comment": "Whether or not cellType is primary (Yes; No)",
"rdfs:label": "IsPrimaryCell",
"rdfs:subClassOf": [
{
Expand All @@ -11212,10 +11237,10 @@
},
"schema:rangeIncludes": [
{
"@id": "bts:TRUE"
"@id": "bts:Yes"
},
{
"@id": "bts:FALSE"
"@id": "bts:No"
}
],
"sms:displayName": "isPrimaryCell",
Expand Down Expand Up @@ -11345,7 +11370,7 @@
{
"@id": "bts:IsMultiIndividual",
"@type": "rdfs:Class",
"rdfs:comment": "Boolean flag indicating whether or not a file has data for multiple individuals (Note: TRUE = Yes; FALSE = No)",
"rdfs:comment": "Whether or not a file has data for multiple individuals (Yes; No)",
"rdfs:label": "IsMultiIndividual",
"rdfs:subClassOf": [
{
Expand All @@ -11357,10 +11382,10 @@
},
"schema:rangeIncludes": [
{
"@id": "bts:TRUE"
"@id": "bts:Yes"
},
{
"@id": "bts:FALSE"
"@id": "bts:No"
}
],
"sms:displayName": "isMultiIndividual",
Expand All @@ -11370,7 +11395,7 @@
{
"@id": "bts:IsMultiSpecimen",
"@type": "rdfs:Class",
"rdfs:comment": "Boolean flag indicating whether or not a file has data for multiple specimens (Note: TRUE = Yes; FALSE = No)",
"rdfs:comment": "Whether or not a file has data for multiple specimens (Yes; No)",
"rdfs:label": "IsMultiSpecimen",
"rdfs:subClassOf": [
{
Expand All @@ -11382,10 +11407,10 @@
},
"schema:rangeIncludes": [
{
"@id": "bts:TRUE"
"@id": "bts:Yes"
},
{
"@id": "bts:FALSE"
"@id": "bts:No"
}
],
"sms:displayName": "isMultiSpecimen",
Expand Down Expand Up @@ -12063,6 +12088,31 @@
"sms:required": "sms:false",
"sms:validationRules": []
},
{
"@id": "bts:IsXenograft",
"@type": "rdfs:Class",
"rdfs:comment": "Whether or not sample source is a xenograft (Yes; No)",
"rdfs:label": "IsXenograft",
"rdfs:subClassOf": [
{
"@id": "bts:ExperimentalData"
}
],
"schema:isPartOf": {
"@id": "http://schema.biothings.io"
},
"schema:rangeIncludes": [
{
"@id": "bts:Yes"
},
{
"@id": "bts:No"
}
],
"sms:displayName": "isXenograft",
"sms:required": "sms:true",
"sms:validationRules": []
},
{
"@id": "bts:Rawcounts",
"@type": "rdfs:Class",
Expand Down Expand Up @@ -14750,7 +14800,7 @@
{
"@id": "bts:FailedQC",
"@type": "rdfs:Class",
"rdfs:comment": "Boolean flag indicating whether the sample or data failed QC checks (Note: TRUE = Yes; FALSE = No)",
"rdfs:comment": "Whether the sample or data failed QC checks (Yes; No)",
"rdfs:label": "FailedQC",
"rdfs:subClassOf": [
{
Expand All @@ -14762,10 +14812,10 @@
},
"schema:rangeIncludes": [
{
"@id": "bts:TRUE"
"@id": "bts:Yes"
},
{
"@id": "bts:FALSE"
"@id": "bts:No"
}
],
"sms:displayName": "failedQC",
Expand Down Expand Up @@ -17643,10 +17693,10 @@
"sms:validationRules": []
},
{
"@id": "bts:TRUE",
"@id": "bts:Yes",
"@type": "rdfs:Class",
"rdfs:comment": "TBD",
"rdfs:label": "TRUE",
"rdfs:label": "Yes",
"rdfs:subClassOf": [
{
"@id": "bts:IsStranded"
Expand All @@ -17655,15 +17705,15 @@
"schema:isPartOf": {
"@id": "http://schema.biothings.io"
},
"sms:displayName": "TRUE",
"sms:displayName": "Yes",
"sms:required": "sms:false",
"sms:validationRules": []
},
{
"@id": "bts:FALSE",
"@id": "bts:No",
"@type": "rdfs:Class",
"rdfs:comment": "TBD",
"rdfs:label": "FALSE",
"rdfs:label": "No",
"rdfs:subClassOf": [
{
"@id": "bts:IsStranded"
Expand All @@ -17672,7 +17722,7 @@
"schema:isPartOf": {
"@id": "http://schema.biothings.io"
},
"sms:displayName": "FALSE",
"sms:displayName": "No",
"sms:required": "sms:false",
"sms:validationRules": []
},
Expand Down
Loading

0 comments on commit f4d789c

Please sign in to comment.